import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import warnings

base = "D:/BE/DL/final code of LP 5/DL/assignmentdl/data/Recurrent Neural Network"

train_data = pd.read_csv(base + "/Stock_Price_Train.csv")

train_data.head()

train = train_data.loc[:, ['Open']].values

train

# Scaling

from sklearn.preprocessing import MinMaxScaler

scaler = MinMaxScaler(feature_range=(0, 1))
train_scaled = scaler.fit_transform(train)
train_scaled

plt.plot(train_scaled)

X_train = []
Y_train = []
timestep = 50
for i in range(timestep, 1258):
    X_train.append(train_scaled[i-timestep:i, 0])
    Y_train.append(train_scaled[i, 0])
X_train, Y_train = np.array(X_train), np.array(Y_train)

X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))

# RNN Model Creation

from keras.models import Sequential
from keras.layers import Dense, SimpleRNN, Dropout

regressor = Sequential()

regressor.add(SimpleRNN(units=50, activation='tanh', return_sequences=True, input_shape = (X_train.shape[1], 1)))
regressor.add(Dropout(0.2))

regressor.add(SimpleRNN(units=50, activation='tanh', return_sequences=True))
regressor.add(Dropout(0.2))

regressor.add(SimpleRNN(units=50, activation='tanh', return_sequences=True))
regressor.add(Dropout(0.2))

regressor.add(SimpleRNN(units=50))
regressor.add(Dropout(0.2))

regressor.add(Dense(units=1))

regressor.summary()

regressor.compile(optimizer='adam', loss='mean_squared_error')

regressor.fit(X_train, Y_train, epochs=25, batch_size=32)

# Testing

test_data = pd.read_csv(base + "/Stock_Price_Test.csv")
test_data.head()

real_stock_price = test_data.loc[:, ['Open']].values

total_data = pd.concat((train_data['Open'], test_data['Open']), axis=0)
inputs = total_data[len(train_data) - len(test_data) - timestep:].values.reshape(-1,1)
inputs = scaler.transform(inputs)

inputs.shape

X_test = []
for i in range(timestep,70):
    X_test.append(inputs[i-timestep:i,0])
X_test = np.array(X_test)
X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))

predicted_stock_price = regressor.predict(X_test)
predicted_stock_price = scaler.inverse_transform(predicted_stock_price)

print(real_stock_price)

print(predicted_stock_price)

# Visualization

plt.plot(real_stock_price, color='red', label='Google Stock Price')
plt.plot(predicted_stock_price, color='blue', label='Predicted Stock Price')
plt.xlabel('Time')
plt.ylabel('Stock Price')
plt.legend()
plt.show()

